A computer vision algorithm for identifying images in different lighting

Computer vision has come a long way since Imagenet, a large, open-source data set of labeled images, was released in 2009 for researchers to use to train AI—but images with tricky or bad lighting can still confuse algorithms.

A new paper by researchers from MIT and DeepMind details a process that can identify images in different lighting without having to hand-code rules or train on a huge data set. The process, called a rendered intrinsics network (RIN), automatically separates an image into reflectance, shape, and lighting layers. It then recombines the layers into a reconstruction of the original images.

AI is learning how to invent new fashions

In a paper published on the ArXiv, researchers from the University of California and Adobe have outlined a way for AI to not only learn a person’s style but create computer-generated images of items that match that style. This kind of computer vision task is being called “predictive fashion” and could let retailers create personalized pieces of clothing.

The model can be used for both personalized recommendation and design. Personalized recommendation is achieved by using a ‘visually aware’ recommender based on Siamese CNNs; generation is achieved by using a Generative Adversarial Net to synthesize new clothing items in the user’s personal style. (Kang et al., 2017).
Reference: Kang, Wang-Cheng, Chen Fang, Zhaowen Wang, and Julian McAuley. “Visually-Aware Fashion Recommendation and Design with Generative Image Models.” arXiv:1711.02231 [Cs], November 6, 2017. http://arxiv.org/abs/1711.02231.

Artificial Intelligence that can create convincing spoof photo and video

I wonder if Peter Burke would rethink the documental and historical status of photography when we start to see AI and Deep Learning systems (like generative adversarial networks – GANs) being used to create fake and believable images at scale.

Reproduction from Ian Goodfellow’s speaking presentation at EmTech MIT 2017.
Reference: J. Snow, “AI could send us back 100 years when it comes to how we consume news,” MIT Technology Review. [Online]. Available: https://www.technologyreview.com/s/609358/ai-could-send-us-back-100-years-when-it-comes-to-how-we-consume-news/. [Accessed: 09-Nov-2017].